Menu
SkillsMP has collected 46 skills from mangowhoiscloud/geode. Open a skill to review its source and details.
Showing 40 of 46 collected skills.
Docs ์ฌ์ดํธ (`site/` Next.js) ์ ๋ณธ๋ฌธ/JSX/markdown ๋งํฌ audit. broken ๋ด๋ถ ๋งํฌ ํ์ง, build-time copy ์ธ์ง, ์ตํธ์ธ HTTP probe. ์ ๊ท ํ์ด์ง ์ถ๊ฐ / slug ์ด์ / chapter ์ญ์ ํ ํ๊ท ๋ฐฉ์ง. Triggered by "broken link", "404", "docs link", "hyperlink", "๋งํฌ ์ ๊ฒ", "๋งํฌ ๊นจ์ง", "audit links", "link checker"โฆ
Source text: Mixed languages
Scope, preregister, execute, audit, normalize, and publish GEODE evaluations with research-question, reproduction, attempt-lineage, trajectory, verifier-receipt, and immutable artifact contracts. Use for benchmark runs or comparisons, eval-artifact andโฆ
GEODE evidence-first development workflow. Use for feature work, provider/model changes, GUI/computer-use work, PDF/document ingestion, observability/schema/event/state changes, verification planning, GitFlow merge prep, and requests to "follow the workflow"โฆ
Add or update a GEODE model or provider from current primary documentation and repository call-site evidence. Use for model IDs, context limits, pricing, reasoning controls, provider routes, capability gates, or fallback changes.
Select complementary review lenses for a requested multi-perspective review or a high-risk GEODE change. Covers design, agent constraints, gateway operations, and CLI/tool behavior; not a mandatory four-agent gate for ordinary edits.
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.
Content-addressed baseline-archive epoch partitioning. Partition baseline_archive.jsonl + the self-improving hub's baseline serving by a HASH of the full baseline-production+measurement spec โ when the spec (margin_rule, fitness/margin logic version, the 4โฆ
Codebase audit + refactoring workflow. Dead code detection, God Object splitting, duplicate function removal, design flaw identification, frontier comparison verification. Triggered by "audit" ("๊ฐ์ฌ"), "dead code" ("๋ฐ๋์ฝ๋"), "refactor" ("๋ฆฌํฉํ ๋ง"), "god object",โฆ
Research process for comparing frontier harnesses (Claude Code, Codex, OpenClaw, autoresearch, Prime Agent) with the original/upstream implementation and performing GAP analysis before feature implementation. Triggered by "research" ("๋ฆฌ์์น"), "gap",โฆ
GEODE CHANGELOG.md management rules. Version releases, change logging, scope determination, format standards. Triggers on "changelog", "release", "version", "๋ฆด๋ฆฌ์ค", "๋ณ๊ฒฝ์ฌํญ", "๋ฒ์ ".
Prepare GEODE worktrees, Korean PRs, CI-gated merges, and guarded cleanup. Use for repository branch, commit, PR, merge, or release work; apply only the stages the user authorized.
Slack Gateway operations guide. Socket Mode credentials, config.toml bindings, serve restart, receiver debugging, reaction behavior. Triggers on "serve", "gateway", "slack", "๋ฐ์ธ๋ฉ", "binding", "์์ผ", "socket", "ํด๋ฌ", "poller", "config.toml".
Code review from the Kent Beck Simple Design 4 Rules perspective. God Object splitting, SRP, duplication removal, naming, cyclomatic complexity. Triggered by "kent beck", "simple design", "simplify", "refactoring" ("๋ฆฌํฉํ ๋ง"), "refactor", "god object", "SRP"โฆ
Trigger when: (1) the user mentions "manim", "scene", "video", "EN/KO render", "GEODE_HERO_LANG", "1080p60", or (2) editing files under `scripts/visualizations/` ending in `.py`, or (3) the user asks to render, re-render, or extend any of the four validatedโฆ
Apply a refined Scandinavian visual system with a neutral black-and-white foundation, restrained sans-serif typography, purposeful product imagery, generous spacing, clear page chapters, and minimal decoration. Use when the user invokes /scandinavian-designโฆ
Diagnose and repair a failed GEODE smoke workflow within the requested acceptance criteria. Preserve failed evidence, verify the shared root cause, and apply merge, rebuild, or live rerun stages only when authorized.
Trigger when: (1) the user mentions "noise", "slop", "frame audit", "video review", "letter spacing", "padding intrusion", "frame extract", "naive arrow", or Korean equivalents (๋ ธ์ด์ฆ, slop, ํ๋ ์ ๊ฒ์, ๊ธ์ ๊นจ์ง), or (2) after rendering a new or modified Manim scene,โฆ
Auto-search and summarize latest AI/agent papers.
Evidence-first multi-step research with bounded parallel collection, contradiction checks, and cited synthesis.
GEODE runtime architecture and repo-shape context. Use for architecture, packaging, release, docs, CI, AgenticLoop, async runtime, and plugin boundary questions.
Automated Git PR review โ diff analysis + quality checks.
Diagnose agent operational failures through default-policy checks, multi-gap analysis, explicit service ownership, request-context lifetime, and degradation-versus-correctness checks.
Verification checklist to prevent fake success. Detects test deletion/disabling, coverage regression, lint bypass, secret exposure. Triggered by "deception", "fake" ("๊ฐ์ง"), "fake success", "verification" ("๊ฒ์ฆ"), "checklist" ("์ฒดํฌ๋ฆฌ์คํธ"), "deletion detection"โฆ
Python code quality review lens. SOLID principles, dead code, exception handling, resource leaks, thread safety, performance. Triggered by "quality" ("ํ์ง"), "SOLID", "dead code" ("๋ฐ๋์ฝ๋"), "exception", "resource leak", "thread safety" keywords.
Review GEODE dependency direction, composition boundaries, circular imports, and optional-dependency loading when changing package or subsystem dependencies.
Mandatory 3-phase explore-reason-act workflow before code modification. Enforces read-before-write, root cause hypothesis formulation, minimal change application. Triggered by "explore" ("ํ์"), "reason" ("์ถ๋ก "), "read before write", "root cause" ("๊ทผ๋ณธ ์์ธ")โฆ
Reference when designing autonomous agent systems or deciding agent freedom/safety/context management/collaboration infrastructure. 10 design principles distilled from Karpathy autoresearch (autonomous ML experiment loop) + AgentHub (agent-native Git DAG).โฆ
Apply GEODE's measured architecture, module and symbol naming, Python type/class, persisted schema, test, site, and versioning conventions. Use when adding or moving modules, choosing dataclass/Pydantic/Protocol/ABC forms, naming classes or files, designingโฆ
Align, run, audit, and publish GEODE benchmark comparisons against Agent-World arXiv 2604.18292v1 across MCP-Mark, BFCL V4, and tau2-bench. Use for Agent-World or AgentWorld comparison requests, cross-suite agent benchmark design, Tau2 comparator/profileโฆ
Use an available Codex MCP integration as a read-only second-opinion verifier for GEODE code reviews, GAP audits, and contract checks. Use only when the user requests Codex cross-checking and the current tool inventory exposes the required MCP tools.
Publish and verify a released GEODE version across GitHub Release and PyPI/uv. Use for uv/uvx distribution, stable promotions, release repair runs, and public installation-channel audits.
Monitor long-running GEODE work, CI, audits, and training without losing output to buffering or confusing a watcher with the underlying state authority.
Agent system design patterns distilled from the OpenClaw codebase. Gateway-centric control, Session Key hierarchy, Binding routing, Lane Queue concurrency, Sub-agent Spawn+Announce, 4-tier automation, Plugin architecture, Policy Chain, Failover strategies.โฆ
GEODE prompt-writing standards. Use when creating or editing runtime prompts, system prompts, tool/developer instructions, model-facing identity text, prompt templates, or scaffold rules that affect model behavior; especially when avoiding identity assertionsโฆ
Ground GEODE design and evaluation work in Stanford CS329A Parts 2 and 5. Use for test-time compute, planning, multi-step reasoning, deep research, LATS, independent subplans, best-of-N, repair depth, measurement replication, verifier authority, andโฆ
Technical blog post writing guide. rooftopsnow.tistory.com style โ Korean formal technical prose, architecture diagrams, code blocks + design intent commentary, table comparisons, checklist wrap-up. Triggers on "blog", "ํฌ์คํ ", "๋ธ๋ก๊ทธ", "๊ธฐ์ ๊ธ", "tech blog".
Audit and improve Generative Engine Optimization as a measurable discovery-to-citation pipeline. Use for /geo, AI-search visibility, citation readiness, and GEO benchmark work.
6-lens diagnostic slop audit โ unused imports, dead private fns, duplicate signatures, abandoned TODOs, lint bypass markers, stale refs.
Design, implement, or evaluate GEODE's GEO capability with source-grounded stage diagnosis, frozen measurement contracts, and no-model preflight before live engine runs.
Design or audit GEODE's dependency-aware grilling flow and slash integration without speculative branch execution or parser-heavy interviews.